Pyramid Stereo Matching Network
Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese networks, lacking
arxiv.org
SPPNet | CNN의 입력 크기 제한 문제 해결 위해 SPP 제안. classification에 활용 |
ParseNet | Global Average Pooling을 도입하여 전역 문맥 정보 통합 |
PSPNet | ParseNet을 확장하여 계층적 전역 정보 추출. Adaptive pooling + 1×1 conv + upsampling + concat 구조 |
댓글 영역